Tour of Go -> Exercise: Web Crawler

exercise-web-crawler.go

package main

import (
	"fmt"
	"sync"
)

type Fetcher interface {
	// Fetch returns the body of URL and
	// a slice of URLs found on that page.
	Fetch(url string) (body string, urls []string, err error)
}

type MutMap struct {
	cache map[string]bool
	mut   sync.Mutex
}

func (m MutMap) Get(key string) bool {
	m.mut.Lock()
	defer m.mut.Unlock()

	_, ok := m.cache[key]
	return ok
}

func (m MutMap) Set(key string, val bool) {
	m.mut.Lock()
	defer m.mut.Unlock()

	m.cache[key] = val
}

// Crawl uses fetcher to recursively crawl
// pages starting with url, to a maximum of depth.
func CrawlParallel(url string, depth int, fetcher Fetcher, cache MutMap, quit chan bool) {
	// check cache for url
	if depth <= 0 || cache.Get(url) {
		quit <- true
		return
	}

	// url not found
	cache.Set(url, true)
	body, urls, err := fetcher.Fetch(url)
	if err != nil {
		fmt.Println(err)
		quit <- true
		return
	}

	fmt.Printf("found: %s %q\n", url, body)

	// launch goroutine for each url
	c := make(chan bool)
	for _, u := range urls {
		go CrawlParallel(u, depth-1, fetcher, cache, c)
	}
	// drain response channel
	for range urls {
		<-c
	}

	quit <- true
}

func main() {
	quit := make(chan bool)

	go CrawlParallel("https://golang.org/", 4, fetcher, MutMap{cache: make(map[string]bool)}, quit)
	<-quit
}

// fakeFetcher is Fetcher that returns canned results.
type fakeFetcher map[string]*fakeResult

type fakeResult struct {
	body string
	urls []string
}

func (f fakeFetcher) Fetch(url string) (string, []string, error) {
	if res, ok := f[url]; ok {
		return res.body, res.urls, nil
	}
	return "", nil, fmt.Errorf("not found: %s", url)
}

// fetcher is a populated fakeFetcher.
var fetcher = fakeFetcher{
	"https://golang.org/": &fakeResult{
		"The Go Programming Language",
		[]string{
			"https://golang.org/pkg/",
			"https://golang.org/cmd/",
		},
	},
	"https://golang.org/pkg/": &fakeResult{
		"Packages",
		[]string{
			"https://golang.org/",
			"https://golang.org/cmd/",
			"https://golang.org/pkg/fmt/",
			"https://golang.org/pkg/os/",
		},
	},
	"https://golang.org/pkg/fmt/": &fakeResult{
		"Package fmt",
		[]string{
			"https://golang.org/",
			"https://golang.org/pkg/",
		},
	},
	"https://golang.org/pkg/os/": &fakeResult{
		"Package os",
		[]string{
			"https://golang.org/",
			"https://golang.org/pkg/",
		},
	},
}